Zhenda Xie

papers

5,571

total citations

papers (12)

Swin Transformer V2: Scaling Up Capacity and Resolution

CVPR 2022arXiv

2,487

citations

SimMIM: A Simple Framework for Masked Image Modeling

CVPR 2022arXiv

1,673

citations

Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning

CVPR 2021arXiv

454

citations

Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation

CVPR 2025arXiv

293

citations

JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation

CVPR 2025arXiv

citations

On Data Scaling in Masked Image Modeling

CVPR 2023arXiv

citations

Parametric Instance Classification for Unsupervised Visual Feature learning

NEURIPS 2020arXiv

citations

Improving CLIP Fine-tuning Performance

ICCV 2023

citations

iCLIP: Bridging Image Classification and Contrastive Language-Image Pre-Training for Visual Recognition

CVPR 2023

citations

Zhenda Xie

papers (12)

Swin Transformer V2: Scaling Up Capacity and Resolution

SimMIM: A Simple Framework for Masked Image Modeling

Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning

Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation

DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior

Revealing the Dark Secrets of Masked Image Modeling

Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation

JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation

On Data Scaling in Masked Image Modeling

Parametric Instance Classification for Unsupervised Visual Feature learning

Improving CLIP Fine-tuning Performance

iCLIP: Bridging Image Classification and Contrastive Language-Image Pre-Training for Visual Recognition

papers (12)

Swin Transformer V2: Scaling Up Capacity and Resolution

SimMIM: A Simple Framework for Masked Image Modeling

Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning

Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation

DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior

Revealing the Dark Secrets of Masked Image Modeling

Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation

JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation

On Data Scaling in Masked Image Modeling

Parametric Instance Classification for Unsupervised Visual Feature learning

Improving CLIP Fine-tuning Performance

iCLIP: Bridging Image Classification and Contrastive Language-Image Pre-Training for Visual Recognition